© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153787
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    0.53
     y
    0.52
    بی
    0.51
     In
    0.51
     alcuni
    0.47
     mo
    0.46
     molt
    0.46
    度の
    0.46
     dissolution
    0.45
     questa
    0.45
    POSITIVE LOGITS
    Council
    0.75
     أول
    0.72
     المجلس
    0.68
    council
    0.65
     Council
    0.62
    Statement
    0.61
     س
    0.60
     మొదటి
    0.57
    Meeting
    0.57
     مجلس
    0.56
    Activations Density 0.000%

    No Known Activations